kuramot6f's picture
Initial release (history squashed)
5fe47a9
Raw History Blame Contribute Delete
22.4 kB
sentencepiece_trainer.cc(78) LOG(INFO) Starts training with :
trainer_spec {
input: /home/kuramoto/ds/unified/tokenizer-v1/build-001/train.txt
input_format:
model_prefix: /home/kuramoto/ds/unified/tokenizer-v1/build-001/tokenizer
model_type: UNIGRAM
vocab_size: 32000
self_test_sample_size: 0
character_coverage: 0.9995
input_sentence_size: 0
shuffle_input_sentence: 0
seed_sentencepiece_size: 1000000
shrinking_factor: 0.75
max_sentence_length: 8192
num_threads: 16
num_sub_iterations: 2
max_sentencepiece_length: 16
split_by_unicode_script: 1
split_by_number: 1
split_by_whitespace: 1
split_digits: 0
pretokenization_delimiter:
treat_whitespace_as_suffix: 0
allow_whitespace_only_pieces: 0
required_chars:
byte_fallback: 1
vocabulary_output_piece_score: 1
train_extremely_large_corpus: 0
seed_sentencepieces_file:
hard_vocab_limit: 1
use_all_vocab: 0
unk_id: 0
bos_id: 1
eos_id: 2
pad_id: 3
unk_piece: <unk>
bos_piece: <s>
eos_piece: </s>
pad_piece: <pad>
unk_surface: ⁇
enable_differential_privacy: 0
differential_privacy_noise_level: 0
differential_privacy_clipping_threshold: 0
}
normalizer_spec {
name: identity
add_dummy_prefix: 0
remove_extra_whitespaces: 0
escape_whitespaces: 1
normalization_rule_tsv:
}
denormalizer_spec {}
trainer_interface.cc(355) LOG(INFO) SentenceIterator is not specified. Using MultiFileSentenceIterator.
trainer_interface.cc(186) LOG(INFO) Loading corpus: /home/kuramoto/ds/unified/tokenizer-v1/build-001/train.txt
trainer_interface.cc(148) LOG(INFO) Loaded 1000000 lines
trainer_interface.cc(148) LOG(INFO) Loaded 2000000 lines
trainer_interface.cc(125) LOG(WARNING) Too many sentences are loaded! (2000000), which may slow down training.
trainer_interface.cc(127) LOG(WARNING) Consider using --input_sentence_size=<size> and --shuffle_input_sentence=true.
trainer_interface.cc(130) LOG(WARNING) They allow to randomly sample <size> sentences from the entire corpus.
trainer_interface.cc(411) LOG(INFO) Loaded all 2000000 sentences
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <unk>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <s>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: </s>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <pad>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x00>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x01>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x02>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x03>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x04>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x05>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x06>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x07>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x08>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x09>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x0A>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x0B>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x0C>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x0D>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x0E>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x0F>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x10>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x11>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x12>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x13>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x14>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x15>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x16>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x17>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x18>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x19>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x1A>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x1B>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x1C>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x1D>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x1E>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x1F>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x20>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x21>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x22>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x23>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x24>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x25>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x26>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x27>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x28>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x29>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x2A>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x2B>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x2C>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x2D>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x2E>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x2F>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x30>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x31>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x32>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x33>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x34>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x35>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x36>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x37>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x38>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x39>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x3A>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x3B>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x3C>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x3D>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x3E>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x3F>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x40>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x41>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x42>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x43>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x44>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x45>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x46>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x47>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x48>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x49>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x4A>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x4B>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x4C>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x4D>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x4E>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x4F>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x50>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x51>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x52>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x53>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x54>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x55>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x56>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x57>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x58>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x59>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x5A>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x5B>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x5C>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x5D>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x5E>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x5F>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x60>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x61>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x62>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x63>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x64>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x65>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x66>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x67>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x68>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x69>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x6A>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x6B>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x6C>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x6D>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x6E>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x6F>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x70>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x71>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x72>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x73>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x74>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x75>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x76>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x77>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x78>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x79>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x7A>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x7B>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x7C>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x7D>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x7E>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x7F>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x80>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x81>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x82>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x83>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x84>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x85>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x86>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x87>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x88>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x89>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x8A>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x8B>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x8C>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x8D>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x8E>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x8F>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x90>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x91>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x92>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x93>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x94>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x95>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x96>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x97>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x98>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x99>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x9A>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x9B>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x9C>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x9D>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x9E>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0x9F>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xA0>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xA1>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xA2>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xA3>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xA4>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xA5>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xA6>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xA7>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xA8>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xA9>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xAA>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xAB>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xAC>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xAD>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xAE>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xAF>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xB0>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xB1>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xB2>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xB3>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xB4>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xB5>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xB6>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xB7>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xB8>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xB9>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xBA>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xBB>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xBC>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xBD>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xBE>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xBF>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xC0>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xC1>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xC2>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xC3>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xC4>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xC5>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xC6>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xC7>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xC8>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xC9>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xCA>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xCB>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xCC>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xCD>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xCE>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xCF>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xD0>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xD1>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xD2>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xD3>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xD4>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xD5>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xD6>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xD7>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xD8>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xD9>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xDA>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xDB>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xDC>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xDD>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xDE>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xDF>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xE0>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xE1>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xE2>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xE3>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xE4>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xE5>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xE6>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xE7>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xE8>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xE9>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xEA>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xEB>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xEC>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xED>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xEE>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xEF>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xF0>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xF1>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xF2>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xF3>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xF4>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xF5>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xF6>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xF7>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xF8>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xF9>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xFA>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xFB>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xFC>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xFD>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xFE>
trainer_interface.cc(427) LOG(INFO) Adding meta_piece: <0xFF>
trainer_interface.cc(432) LOG(INFO) Normalizing sentences...
trainer_interface.cc(541) LOG(INFO) all chars count=70242767
trainer_interface.cc(552) LOG(INFO) Done: 99.95% characters are covered.
trainer_interface.cc(562) LOG(INFO) Alphabet size=10978
trainer_interface.cc(563) LOG(INFO) Final character coverage=0.9995
trainer_interface.cc(594) LOG(INFO) Done! preprocessed 2000000 sentences.
unigram_model_trainer.cc(265) LOG(INFO) Making suffix array...
unigram_model_trainer.cc(269) LOG(INFO) Extracting frequent sub strings... node_num=17213124
unigram_model_trainer.cc(312) LOG(INFO) Initialized 1010978 seed sentencepieces
trainer_interface.cc(600) LOG(INFO) Tokenizing input sentences with whitespace: 2000000
trainer_interface.cc(611) LOG(INFO) Done! 2033334
unigram_model_trainer.cc(602) LOG(INFO) Using 2033334 sentences for EM training
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=0 size=941672 obj=203.211 num_tokens=37774628 num_tokens/piece=40.1144
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=1 size=906794 obj=197.107 num_tokens=38190977 num_tokens/piece=42.1165
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=0 size=679984 obj=197.288 num_tokens=38932777 num_tokens/piece=57.2554
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=1 size=679636 obj=196.866 num_tokens=39133710 num_tokens/piece=57.5804
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=0 size=509712 obj=197.694 num_tokens=40137202 num_tokens/piece=78.7449
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=1 size=509700 obj=197.151 num_tokens=40244587 num_tokens/piece=78.9574
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=0 size=382272 obj=198.435 num_tokens=41488504 num_tokens/piece=108.531
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=1 size=382272 obj=197.743 num_tokens=41565497 num_tokens/piece=108.733
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=0 size=286699 obj=199.449 num_tokens=42905361 num_tokens/piece=149.653
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=1 size=286699 obj=198.7 num_tokens=42962011 num_tokens/piece=149.851
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=0 size=215022 obj=200.681 num_tokens=44293788 num_tokens/piece=205.997
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=1 size=215022 obj=199.948 num_tokens=44336194 num_tokens/piece=206.194
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=0 size=161265 obj=202.114 num_tokens=45671763 num_tokens/piece=283.209
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=1 size=161264 obj=201.404 num_tokens=45704260 num_tokens/piece=283.413
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=0 size=120948 obj=203.697 num_tokens=47068111 num_tokens/piece=389.16
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=1 size=120948 obj=203.003 num_tokens=47095994 num_tokens/piece=389.39
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=0 size=90710 obj=205.377 num_tokens=48469686 num_tokens/piece=534.337
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=1 size=90710 obj=204.702 num_tokens=48484501 num_tokens/piece=534.5
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=0 size=68032 obj=207.131 num_tokens=49891376 num_tokens/piece=733.352
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=1 size=68032 obj=206.455 num_tokens=49903769 num_tokens/piece=733.534
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=0 size=51024 obj=208.947 num_tokens=51420025 num_tokens/piece=1007.76
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=1 size=51024 obj=208.213 num_tokens=51431560 num_tokens/piece=1007.99
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=0 size=38268 obj=210.84 num_tokens=53068742 num_tokens/piece=1386.77
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=1 size=38268 obj=210.04 num_tokens=53090325 num_tokens/piece=1387.33
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=0 size=35200 obj=210.826 num_tokens=53605405 num_tokens/piece=1522.88
unigram_model_trainer.cc(618) LOG(INFO) EM sub_iter=1 size=35200 obj=210.581 num_tokens=53617476 num_tokens/piece=1523.22
trainer_interface.cc(689) LOG(INFO) Saving model: /home/kuramoto/ds/unified/tokenizer-v1/build-001/tokenizer.model
trainer_interface.cc(701) LOG(INFO) Saving vocabs: /home/kuramoto/ds/unified/tokenizer-v1/build-001/tokenizer.vocab